dart-retro

dart-retro is a command for Claude Code from dartsim/dart. It costs 12 tokens per session (664 once invoked), scanned A, original, BSD-2-Clause.

A workflow for reviewing completed work and recording lessons that could help future contributors or coding agents. It keeps only reusable findings, such as recurring mistakes or workflow problems.

In plain words
What is it for?
Use it to inspect a finished task, find durable patterns or failure modes, and route those lessons into the project's shared documentation.
Why use it?
It prevents useful lessons from being lost after a task ends and avoids adding notes when the work revealed nothing broadly reusable.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: agent in frontmatter; mentions AGENTS.md.

About the project

DART is an open-source C++23 physics engine that simulates the movement and interactions of articulated rigid-body systems for robotics, animation, and machine learning. Researchers and developers use it for kinematics, dynamics, collision handling, constraints, and loading robot models, with C++ and Python interfaces. The catalogue add-ons support workflows built around this engine.

dartsim/dart · 1,201 stars · on GitHub · dart.readthedocs.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/dartsim/dart/dart-retro
Clone the repo
git clone --depth 1 https://github.com/dartsim/dart

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dart-retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/dartsim/dart/dart-retro.svg)](https://agentmods.dev/commands/dartsim/dart/dart-retro)
Your own site
<a href="https://agentmods.dev/commands/dartsim/dart/dart-retro"><img src="https://agentmods.dev/badge/commands/dartsim/dart/dart-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00664
Opus 5 $0.00006 $0.00332
Sonnet 5 $0.00002 $0.00133
Haiku 4.5 $0.00001 $0.00066

Measured today against content hash 350911722017, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dart-retro scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/dart-retro.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve future task execution through a retrospective: $ARGUMENTS

Use the original request and session evidence to improve the harness for future similar tasks: better quality, completeness, or efficiency. Successful, unsatisfactory, incomplete, and blocked outcomes qualify. PR merge and dev-task retirement do not alone establish that the user's goal was met.

Required Reading

@AGENTS.md @docs/AGENTS.md @docs/ai/principles.md @docs/ai/components.md @docs/ai/verification.md

Load task owners as needed. Read docs/onboarding/ai-tools.md for tool/runtime questions and before controlled agent runs. docs/ai/components.md owns placement of accepted learnings; this workflow owns the retrospective method.

Skip If

Conclude without harness edits when the evidence supports no reusable improvement: existing guidance already covers the lesson and is discoverable, the finding is task-specific, or no change has a supported benefit. State why and report missing evidence; success, failure, or a merged PR alone is not a skip condition.

Workflow

  1. Reconstruct intent and outcome. Default to the current session. Compare the initial request and later scope decisions with artifacts and results. Inspect relevant history around decisions, corrections, and failures, including substantive domain work before CI/review/closeout. State missing evidence; do not load every log by default.
  2. Find the harness contribution. Connect useful decisions, rework, missed requirements, and wasted context/tool cycles to instructions, routing, tools, or gates. Separate observations from inferred causes, implementation bugs, and external blockers. Check existing owners and executable coverage before proposing rules; investigate why existing guidance was missed.
  3. Choose a testable improvement. State the observed decision, causal gap, owner, and what an agent starting from the same brief should do differently. Name the expected benefit, a check that could disprove it, and successful constraints to preserve.
  4. Improve existing owners. Prefer removal, consolidation, or rewriting to appending rules or files; repair discovery when guidance already exists. Follow docs/ai/components.md for placement and adapter regeneration. Keep session identifiers out of durable guidance. Preserve model/effort/action limits; a retrospective does not reopen the original implementation or authorize new GitHub mutations.
  5. Validate proportionately. For consequential instruction changes, replay the observed decision and a contrasting similar task; use fresh controlled agents when permitted and useful. Distinguish structural checks, predicted benefits, and measured outcomes. Run the relevant gates in docs/ai/verification.md and pixi run lint before committing.

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +7 lines · +5 tokens per session 350911722017
  2. 2d ago Changed · -3 lines 6fc75b4f1064
  3. 4d ago First seen · 63 lines · 7 tokens per session scan A 24d195b17c05

Subscribe to this mod's changes

dart-retro is a command published in the GitHub repository dartsim/dart (1,201 stars, last pushed today), licensed BSD-2-Clause. It adds 12 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.